datasets/v2.6.2/en/audio_process.html

<meta charset="utf-8" /><meta http-equiv="content-security-policy" content=""><meta name="hf:doc:metadata" content="{&quot;local&quot;:&quot;process-audio-data&quot;,&quot;sections&quot;:[{&quot;local&quot;:&quot;cast&quot;,&quot;title&quot;:&quot;Cast&quot;},{&quot;local&quot;:&quot;map&quot;,&quot;title&quot;:&quot;Map&quot;}],&quot;title&quot;:&quot;Process audio data&quot;}" data-svelte="svelte-1phssyn">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/assets/pages/__layout.svelte-hf-doc-builder.css">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/start-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/chunks/vendor-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/chunks/paths-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/pages/__layout.svelte-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/pages/audio_process.mdx-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/chunks/IconCopyLink-hf-doc-builder.js">
	<link rel="modulepreload" href="/docs/datasets/v2.6.2/en/_app/chunks/CodeBlock-hf-doc-builder.js"> 





<h1 class="relative group"><a id="process-audio-data" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#process-audio-data"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Process audio data
	</span></h1>

<p>This guide shows specific methods for processing audio datasets. Learn how to:</p>
<ul><li>Resample the sampling rate.</li>
<li>Use <a href="/docs/datasets/v2.6.2/en/package_reference/main_classes#datasets.Dataset.map">map()</a> with audio datasets.</li></ul>
<p>For a guide on how to process any type of dataset, take a look at the <a class="underline decoration-sky-400 decoration-2 font-semibold" href="./process">general process guide</a>.</p>
<h2 class="relative group"><a id="cast" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#cast"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Cast
	</span></h2>

<p>The <a href="/docs/datasets/v2.6.2/en/package_reference/main_classes#datasets.Dataset.cast_column">cast_column()</a> function is used to cast a column to another feature to be decoded. When you use this function with the <a href="/docs/datasets/v2.6.2/en/package_reference/main_classes#datasets.Audio">Audio</a> feature, you can resample the sampling rate:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> datasets <span class="hljs-keyword">import</span> load_dataset, Audio

<span class="hljs-meta">&gt;&gt;&gt; </span>dataset = load_dataset(<span class="hljs-string">&quot;PolyAI/minds14&quot;</span>, <span class="hljs-string">&quot;en-US&quot;</span>, split=<span class="hljs-string">&quot;train&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset = dataset.cast_column(<span class="hljs-string">&quot;audio&quot;</span>, Audio(sampling_rate=<span class="hljs-number">16000</span>))<!-- HTML_TAG_END --></pre></div>
<p>Audio files are decoded and resampled on-the-fly, so the next time you access an example, the audio file is resampled to 16kHz:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span>dataset[<span class="hljs-number">0</span>][<span class="hljs-string">&quot;audio&quot;</span>]
{<span class="hljs-string">&#x27;array&#x27;</span>: array([ <span class="hljs-number">2.3443763e-05</span>,  <span class="hljs-number">2.1729663e-04</span>,  <span class="hljs-number">2.2145823e-04</span>, ...,
         <span class="hljs-number">3.8356509e-05</span>, -<span class="hljs-number">7.3497440e-06</span>, -<span class="hljs-number">2.1754686e-05</span>], dtype=float32),
 <span class="hljs-string">&#x27;path&#x27;</span>: <span class="hljs-string">&#x27;/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~JOINT_ACCOUNT/602ba55abb1e6d0fbce92065.wav&#x27;</span>,
 <span class="hljs-string">&#x27;sampling_rate&#x27;</span>: <span class="hljs-number">16000</span>}<!-- HTML_TAG_END --></pre></div>
<div class="flex justify-center"><img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/resample.gif">
    <img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/resample-dark.gif"></div>
<h2 class="relative group"><a id="map" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#map"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a>
	<span>Map
	</span></h2>

<p>The <a href="/docs/datasets/v2.6.2/en/package_reference/main_classes#datasets.Dataset.map">map()</a> function helps preprocess your entire dataset at once. Depending on the type of model you’re working with, you’ll need to either load a <a href="https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoFeatureExtractor" rel="nofollow">feature extractor</a> or a <a href="https://huggingface.co/docs/transformers/model_doc/auto#transformers.AutoProcessor" rel="nofollow">processor</a>.</p>
<ul><li><p>For pretrained speech recognition models, load a feature extractor and tokenizer and combine them in a <code>processor</code>:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoTokenizer, AutoFeatureExtractor, AutoProcessor

<span class="hljs-meta">&gt;&gt;&gt; </span>model_checkpoint = <span class="hljs-string">&quot;facebook/wav2vec2-large-xlsr-53&quot;</span>
<span class="hljs-comment"># after defining a vocab.json file you can instantiate a tokenizer object:</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>tokenizer = AutoTokenizer(<span class="hljs-string">&quot;./vocab.json&quot;</span>, unk_token=<span class="hljs-string">&quot;[UNK]&quot;</span>, pad_token=<span class="hljs-string">&quot;[PAD]&quot;</span>, word_delimiter_token=<span class="hljs-string">&quot;|&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>feature_extractor = AutoFeatureExtractor.from_pretrained(model_checkpoint)
<span class="hljs-meta">&gt;&gt;&gt; </span>processor = AutoProcessor.from_pretrained(feature_extractor=feature_extractor, tokenizer=tokenizer)<!-- HTML_TAG_END --></pre></div></li>
<li><p>For fine-tuned speech recognition models, you only need to load a <code>processor</code>:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoProcessor

<span class="hljs-meta">&gt;&gt;&gt; </span>processor = AutoProcessor.from_pretrained(<span class="hljs-string">&quot;facebook/wav2vec2-base-960h&quot;</span>)<!-- HTML_TAG_END --></pre></div></li></ul>
<p>When you use <a href="/docs/datasets/v2.6.2/en/package_reference/main_classes#datasets.Dataset.map">map()</a> with your preprocessing function, include the <code>audio</code> column to ensure you’re actually resampling the audio data:</p>

	<div class="code-block relative"><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg>
	<div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div>
	Copied</div></button></div>
	<pre><!-- HTML_TAG_START --><span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">def</span> <span class="hljs-title function_">prepare_dataset</span>(<span class="hljs-params">batch</span>):
<span class="hljs-meta">... </span>    audio = batch[<span class="hljs-string">&quot;audio&quot;</span>]
<span class="hljs-meta">... </span>    batch[<span class="hljs-string">&quot;input_values&quot;</span>] = processor(audio[<span class="hljs-string">&quot;array&quot;</span>], sampling_rate=audio[<span class="hljs-string">&quot;sampling_rate&quot;</span>]).input_values[<span class="hljs-number">0</span>]
<span class="hljs-meta">... </span>    batch[<span class="hljs-string">&quot;input_length&quot;</span>] = <span class="hljs-built_in">len</span>(batch[<span class="hljs-string">&quot;input_values&quot;</span>])
<span class="hljs-meta">... </span>    <span class="hljs-keyword">with</span> processor.as_target_processor():
<span class="hljs-meta">... </span>        batch[<span class="hljs-string">&quot;labels&quot;</span>] = processor(batch[<span class="hljs-string">&quot;sentence&quot;</span>]).input_ids
<span class="hljs-meta">... </span>    <span class="hljs-keyword">return</span> batch
<span class="hljs-meta">&gt;&gt;&gt; </span>dataset = dataset.<span class="hljs-built_in">map</span>(prepare_dataset, remove_columns=dataset.column_names)<!-- HTML_TAG_END --></pre></div>


		<script type="module" data-hydrate="niooxi">
		import { start } from "/docs/datasets/v2.6.2/en/_app/start-hf-doc-builder.js";
		start({
			target: document.querySelector('[data-hydrate="niooxi"]').parentNode,
			paths: {"base":"/docs/datasets/v2.6.2/en","assets":"/docs/datasets/v2.6.2/en"},
			session: {},
			route: false,
			spa: false,
			trailing_slash: "never",
			hydrate: {
				status: 200,
				error: null,
				nodes: [
					import("/docs/datasets/v2.6.2/en/_app/pages/__layout.svelte-hf-doc-builder.js"),
						import("/docs/datasets/v2.6.2/en/_app/pages/audio_process.mdx-hf-doc-builder.js")
				],
				params: {}
			}
		});
	</script>